3D Gaussian Splatting in a Weekend

After seeing the fixed 3rd order spherical harmonics I was curious how that might be optimized. DropAnSH-GS (Feb 2026) drops out high order SH coefficients to force low frequency color into low order coefficients (3.4. Spherical Harmonics Dropout). They conclude that high order coefficients can be discarded to trade off speed/size for detail. They don’t seem to have considered encoding as sparse coefficients post training to discard all near zero coefficients.

https://arxiv.org/pdf/2602.20933

How does 3DGS differ from a point cloud that is produced by Lidar or KinectV2?